Home / Publications / Overfitting in machine learning models for predicting partial atomic charges of drug-like molecules

Overfitting in machine learning models for predicting partial atomic charges of drug-like molecules

Denis Vadimovich Zverev 1
Denis Vadimovich Zverev
, 
Polina K. Nikiforova 1
Polina K. Nikiforova
, 
Arslan Ramilevich Shaimardanov 1
Arslan Ramilevich Shaimardanov
,  , 
Vladimir Alexandrovich Palyulin 1
Vladimir Alexandrovich Palyulin
10.71267/mencom.7930
Published 2026-03-24
Communication , Volume 36, Issue 3, 257-259
0
Share
Cite this
GOST
 | 
Cite this
GOST Copy
Zverev D. V. et al. Overfitting in machine learning models for predicting partial atomic charges of drug-like molecules // Mendeleev Communications. 2026. Vol. 36. No. 3. pp. 257-259.
GOST all authors (up to 50) Copy
Zverev D. V., Nikiforova P. K., Shaimardanov A. R., Shulga D. A., Palyulin V. A. Overfitting in machine learning models for predicting partial atomic charges of drug-like molecules // Mendeleev Communications. 2026. Vol. 36. No. 3. pp. 257-259.
RIS
 | 
Cite this
RIS Copy
TY - JOUR
DO - 10.71267/mencom.7930
UR - https://mendcomm.colab.ws/publications/10.71267/mencom.7930
TI - Overfitting in machine learning models for predicting partial atomic charges of drug-like molecules
T2 - Mendeleev Communications
AU - Zverev, Denis Vadimovich
AU - Nikiforova, Polina K.
AU - Shaimardanov, Arslan Ramilevich
AU - Shulga, Dmitry Alexandrovich
AU - Palyulin, Vladimir Alexandrovich
PY - 2026
DA - 2026/03/24
PB - Mendeleev Communications
SP - 257-259
IS - 3
VL - 36
ER -
BibTex
 | 
Cite this
BibTex (up to 50 authors) Copy
@article{2026_Zverev,
author = {Denis Vadimovich Zverev and Polina K. Nikiforova and Arslan Ramilevich Shaimardanov and Dmitry Alexandrovich Shulga and Vladimir Alexandrovich Palyulin},
title = {Overfitting in machine learning models for predicting partial atomic charges of drug-like molecules},
journal = {Mendeleev Communications},
year = {2026},
volume = {36},
publisher = {Mendeleev Communications},
month = {Mar},
url = {https://mendcomm.colab.ws/publications/10.71267/mencom.7930},
number = {3},
pages = {257--259},
doi = {10.71267/mencom.7930}
}
MLA
Cite this
MLA Copy
Zverev, Denis Vadimovich, et al. “Overfitting in machine learning models for predicting partial atomic charges of drug-like molecules.” Mendeleev Communications, vol. 36, no. 3, Mar. 2026, pp. 257-259. https://mendcomm.colab.ws/publications/10.71267/mencom.7930.
Views
1

Keywords

chemical datasets
drug-like molecules
machine learning
multilayer perceptron
neural network
overfitting
partial atomic charges
random forest
transferability

Abstract

Overfitting in machine learning models for partial atomic charges was investigated for highly heterogeneous datasets common in medicinal chemistry. Random forest and multilayer perceptron models were trained and validated on a specially clustered dataset of drug-like molecules. Analysis of standard quality metrics for reproducing RESP charges showed that the trained models exhibit no evidence of overfitting.

Funders

Ministry of Education and Science of the Russian Federation
121021000105-7

References

1.
Classical Electrostatics for Biomolecular Simulations
Cisneros G.A., Karttunen M., Ren P., Sagui C.
Chemical Reviews, 2013
6.
A well-behaved electrostatic potential based method using charge restraints for deriving atomic charges: the RESP model
Bayly C.I., Cieplak P., Cornell W., Kollman P.A.
The Journal of Physical Chemistry, 1993
11.
Electronegativity equalization: application and parametrization
Mortier W.J., Van Genechten K., Gasteiger J.
Journal of the American Chemical Society, 1985
12.
Fast tools for calculation of atomic charges well suited for drug design
Shulga D.A., Oliferenko A.A., Pisarev S.A., Palyulin V.A., Zefirov N.S.
SAR and QSAR in Environmental Research, 2008
14.
Atomic charges for variable molecular conformations
Reynolds C.A., Essex J.W., Richards W.G.
Journal of the American Chemical Society, 1992
15.
Machine learning methods in chemoinformatics
Mitchell J.B.
Wiley Interdisciplinary Reviews: Computational Molecular Science, 2014
16.
Artificial Intelligence, Machine Learning, and Deep Learning in Real-Life Drug Design Cases
Muller C., Rabal O., Diaz Gonzalez C.
Methods in Molecular Biology, 2021
17.
Extending machine learning beyond interatomic potentials for predicting molecular properties
Fedik N., Zubatyuk R., Kulichenko M., Lubbers N., Smith J.S., Nebgen B., Messerly R., Li Y.W., Boldyrev A.I., Barros K., Isayev O., Tretiak S.
Nature Reviews Chemistry, 2022
18.
Machine Learning in Chemoinformatics and Medicinal Chemistry
Rodríguez-Pérez R., Miljković F., Bajorath J.
Annual Review of Biomedical Data Science, 2022
19.
Overfitting and undercomputing in machine learning
Dietterich T.
ACM Computing Surveys, 2002
20.
An Overview of Overfitting and its Solutions
Ying X.
Journal of Physics: Conference Series, 2019
21.
Ab Initio Machine Learning in Chemical Compound Space
Huang B., von Lilienfeld O.A.
Chemical Reviews, 2021
22.
Identifying and embedding transferability in data-driven representations of chemical space
Gould T., Chan B., Dale S.G., Vuckovic S.
Chemical Science, 2024
24.
Self-Consistent Parameterization of DNA Residues for the Non-Polarizable AMBER Force Fields
Schneider A.L., Albrecht A.V., Huang K., Germann M.W., Poon G.M.
Life, 2022
25.
A fast and high-quality charge model for the next generation general AMBER force field
He X., Man V.H., Yang W., Lee T., Wang J.
Journal of Chemical Physics, 2020
26.
OPLS4: Improving Force Field Accuracy on Challenging Regimes of Chemical Space
Lu C., Wu C., Ghoreishi D., Chen W., Wang L., Damm W., Ross G.A., Dahlgren M.K., Russell E., Von Bargen C.D., Abel R., Friesner R.A., Harder E.D.
Journal of Chemical Theory and Computation, 2021